爬取酷狗音乐周杰伦的专辑

简介

看到别人写的爬虫采集mm图，有那么多人给币，本菜鸡也想写点东西分享一下，就想下载些音乐，经过长时间的分析，终于完成了。

开发环境

• python3.8解释器

• Pycharm 编辑器

  所使用模块

• import requests
• import re
• import json
• import logging
• from os import makedirs
• from os.path import exists

抓取的页面

代码实现

import requests
import re
import json
import logging
from os import makedirs
from os.path import exists

logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s %(levelname)s %(filename)s:%(lineno)s >>> %(message)s',
                    datefmt='%Y-%m-%d %H:%M:%S',)
BASE_URL = 'https://www.kugou.com'


def save_data(data, path, name):
    exists(path) or makedirs(path)
    data_path = f'{path}/{name}.mp3'
    print(data_path)
    with open(data_path, 'wb')as f:
        f.write(data)


def get_page(url):
    headers = {
        'cookie': '自己填',
        'referer': 'https://www.kugou.com/',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    }
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            # print(response.text)
            return response.text
        logging.error('在地址为: %s 时遇到错误的状态码', response.status_code, url)
    except requests.RequestException:
        logging.error('抓取此链接发生错误 %s', url, exc_info=True)


# 通过解析页面数据获取音频的api接口链接，再请求接口链接得到mp3链接
def parse_data(html):
    pattern = re.compile(r'var data=(.*);')
    data = re.findall(pattern, html)[0]
    dit_data = json.loads(data)
    play_urls = []
    audio_names = []
    album_names = []
    for info in dit_data:
        album_name = info['album_name']
        author_name = info['author_name']
        audio_name = info['audio_name']
        encode_album_audio_id = info['encode_album_audio_id']
        audio_detail_url = f'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&dfid=1txkVX3n2MQE49Pvux0mAsuT&appid=1014&mid=b2d248b4902c623a204e0410004e70d0&platid=4&encode_album_audio_id={encode_album_audio_id}'
        logging.info('处理接口链接为: %s', audio_detail_url)
        audio_name = f'{author_name}-{audio_name}'
        # 通过请求音乐接口链接再解析得到MP3播放地址
        audio_info_html = get_page(audio_detail_url)
        detail_data = json.loads(audio_info_html)
        play_url = detail_data['data']['play_url']
        play_urls.append(play_url)
        audio_names.append(audio_name)
        album_names.append(album_name)
    datas = play_urls, audio_names, album_names
    yield datas


def download(data):
    for play_url, audio_name, name in data:
        audio_content = requests.get(play_url).content
        save_data(audio_content, name, audio_name)
        logging.info('正在保存--> %s', audio_name)


def main():
    url = 'https://www.kugou.com/album/info/yhaz39/'
    html_data = get_page(url)
    data = parse_data(html_data)  # 生成器对象
    logging.info('获得包含mp3，歌名，专辑名的生成器对象 >>> %s', data)
    for i in data:
        mp3_info_data = list(zip(i[0], i[1], i[2]))
        download(mp3_info_data)


if __name__ == '__main__':
    main()

执行结果：

大家可以去试试哦，白嫖的，不要白不要。